Showing papers in "Journal of Advanced Computational Intelligence and Intelligent Informatics in 2008"

Fuzzy Inference based Mentality Expression for Eye Robot in Affinity Pleasure-Arousal Space

Abstract: An eye robot focused on eye expression and a mascot robot system are proposed as a casual communication robot systems with human friendly expression. A mentality expression system based on the affinity pleasure-arousal space by eye robot is proposed. The three-dimensional affinity pleasure-arousal space is proposed to express mentality states with fuzzy inference. The eye robot that performs eye motions is developed based on the human mechanisms. A mascot robot system is proposed as an internet-based robot application for casual communication in home environment. This mascot robot system is a network composed of four fixed type eye robots, one mobile self-propelled type eye robot, an information recommendation module, and the speech recognition module. The mascot robot system’s functionality is demonstrated in a living room, where casual communication is conducted based on speech recognition and mentality expression of eye robots. The validity of the proposed mentality expression system is confirmed by communication experiments with 2 scenarios. The proposed systems provide casual communication between a human interlocutor and a robot.

Time Related Association Rules Mining with Attributes Accumulation Mechanism and its Application to Traffic Prediction

Abstract: We propose a method of association rule mining using genetic network programming (GNP) with time series processing mechanism and attribute accumulation mechanism in order to find time related sequence rules efficiently in association rule extraction systems. We suppose that, the database consists of a large number of attributes based on time series. In order to deal with databases which have a large number of attributes, GNP individual accumulates better attributes in it gradually round by round, and the rules of each round are stored in the Small Rule Pool using hash method, and the new rules will be finally stored in the Big Rule Pool. The aim of this paper is to better handle association rule extraction of the database in many time-related applications especially in the traffic prediction problem. In this paper, the algorithm capable of finding the important time related association rules is described and experimental results considering a traffic prediction problem are presented.

Favoring Consensus and Penalizing Disagreement in Group Decision Making

Abstract: In this paper we introduce a multi-stage decision making procedure where decision makers’ opinions are weighted by their contribution to the agreement after they sort alternatives into a fixed finite scale given by linguistic categories, each one having an associated numerical score. We add scores obtained for each alternative using an aggregation operator. Based on distances among vectors of individual and collective scores, we assign an index to decision makers showing their contributions to the agreement. Opinions of negative contributors are excluded and the process is reinitiated until all decision makers contribute positively to the agreement. To obtain the final collective weak order on the set of alternatives, we weigh the scores that decision makers assign to alternatives by indices corresponding to their contribution to the agreement.

State Dependant Anytime Control Methodology for Non-Linear Systems

Abstract: Nowadays in solving control problems the processing is performed typically by model-based computer systems, which contain a representation of our knowledge about the nature and the actual circumstances of the problem in hand. If the nature and/or the actual circumstances change, the corresponding model should also be changed. Anytime techniques are very flexible in this respect and can advantageously be used when the operation should be performed under changing circumstances. In this paper, a nonlinear state dependant control methodology is proposed for anytime use and as an example is applied to globally stabilize a given prototypical aeroelastic wing section via one control surface.

A Genetic Network Programming Based Method to Mine Generalized Association Rules with Ontology

Abstract: In this paper, we propose a genetic network programming based method to mine generalized association rules with ontology. We first introduce ontology to facilitate building the multi concept layers and propose dynamic threshold approach (DTA) to equalize the different layers. We make use of an evolutionary computation method genetic network programming (GNP) to mine the rules. Two kinds of fitness functions each with four kinds of policies and a new genetic operator are developed to speed up searching the rule space.

Comparative Association Rules Mining Using Genetic Network Programming (GNP) with Attributes Accumulation Mechanism and its Application to Traffic Systems

Abstract: In this paper, we present a method of comparative association rules mining using Genetic Network Programming (GNP) with attributes accumulation mechanism in order to uncover association rules between different datasets. GNP is an evolutionary approach which can evolve itself and find the optimal solutions. The motivation of the comparative association rules mining method is to use the data mining approach to check two or more databases instead of one, so as to find the hidden relations among them. The proposed method measures the importance of association rules by using the absolute difference of confidences among different databases and can get a number of interesting rules. Association rules obtained by comparison can help us to find and analyze the explicit and implicit patterns among a large amount of data. For the large attributes case, the calculation is very time-consuming, when the conventional GNP based data mining is used. So, we have proposed an attribute accumulation mechanism to improve the performance. Then, the comparative association rules mining using GNP has been applied to a complicated traffic system. By mining and analyzing the rules under different traffic situations, it was found that we can get interesting information of the traffic system.

Haar Wavelets for Online-Game Player Classification with Dynamic Time Warping

Abstract: Online game players’ action sequences, while important to understand their behavior, usually contain noise and/or redundancy, making them unnecessarily long. To acquire briefer sequences representative of players’ features, we apply the Haar wavelet transform to action sequences and reconstruct them from selected wavelet coefficients. Results indicate that this approach is effective in classificationwhen the k-nearest neighbor classifier is used to classify players based on dynamic time warping distances between reconstructed sequences.

Neuro-Fuzzy Approaches for Forecasting Electrical Load Using Additional Moving Average Window Data Filter on Takagi-Sugeno Type MISO Networks

Abstract: The paper describes a Neuro-fuzzy approach with additional moving average window data filter and fuzzy clustering algorithm that can be used to forecast electrical load using the Takagi-Sugeno (TS) type multi-input single-output (MISO) neurofuzzy network efficiently. The training algorithm is efficient in the sense that it can bring the performance index of the network, such as the sum squared error (SSE), down to the desired error goal much faster than that the simple LevenbergMarquardt algorithm (LMA). Finally, the above training algorithm is tested on neuro-fuzzy modeling and long-term forecasting application of Electrical load time series.

On-Line Fault Detection and Compensation of Hydraulic Driven Machines Using Modelling Techniques

Abstract: The development of on line model-based fault detection systems in machinery improves the operational reliability of industrial systems and reduces the operational and maintenance costs. In this direction, this paper presents the use of modelling information to determine changes in characteristics from measured data for the fault detection purpose of hydraulic driven machines as well as for the compensation of incipient faults where applicable. For this purpose a suitable implementation environment was developed that allows the on line interaction of real time data and simulation results and makes possible their direct effect to the actual system.